전체 검색

AI 모델 84759

• TerraMind-1.0-Tokenizer-S2L2A↗

  ibm-esa-geospatial

  TerraMind is the first multimodal any-to-any generative foundation model for Earth Observation jointly developed by IBM, ESA, and Forschungszentrum Jülich. The model is pre-trained using FSQ-VAE tokens as targets. This tokenizer encodes and decodes Sentinel-2 L2A satellite images for the TerraMind model. The tokenizer uses FSQ with five dimensions and a codebook size of 15'360 tokens. The decoding process uses diffusion steps for the reconstruction. The model was pre-trained for 100 epochs on nine million S-2 L2A images from the TerraMesh dataset. The tokenizer is fully integrated into the fine-tuning toolkit TerraTorch. You can initialize the pre-trained tokenizer with:

• Huihui-GLM-5.3-Flash-abliterated-GGUF↗

  Ihnenko

• Qwopus3.6-27B-Coder-Compat-MTP-GGUF↗

  Jackrong

  Bundled-MTP GGUF release with expanded chat-template interoperability for tool-using runtimes and OpenAI-compatible agent histories. ✓ JSON-string arguments ✓ Mapping & list arguments ✓ llama.cpp / minja ✓ Hugging Face Jinja ⚡ Bundled MTP 🧠 Weight-identical validation This edition expands interoperability across agent frameworks that store historical tool_call.function.arguments in different valid representations. The embedded template accepts pre-serialized JSON strings as well as structured mappings and lists, while preserving the original tool-call payload. This is a template-level compatibility update: model weights and the bundled MTP prediction tensors remain unchanged.

• DeepSeek-V4.1-Flash-1017-EXL3-2.8bpw↗

  jayleaton

• Qwen3.8-3.6-27B-blend-GGUF↗

  JetBrains

  **Unofficial JetBrains derivative.** This model was prepared by JetBrains using Qwen models developed by Alibaba Cloud. This release is not affiliated with, sponsored by, or endorsed by Alibaba Cloud or Alibaba Group. *Tasks completed versus output tokens on JetBrains’ 100-task internal coding benchmark. Reasoning settings differ between configurations; see the article for methodology and context.* Read Making Local AI Smarter and Faster for the Junie Local release story, coding evaluations, token-efficiency results, and MTP runtime experiments.

• exaone-verireason-matched550-luna-fullft-e5-seed42↗

  Jongbin-kr

• LCO-Embedding-Omni-3B↗

  LCO-Embedding

• llm-compiler-7b-ftd-IMat-GGUF↗

  legraphista

• japanese-large-lm-3.6b-instruction-sft↗

  line-corporation

• Qwen2-Math-72B-Instruct-GGUF↗

  lmstudio-community